Scribd
Upload
279 views9 pages

Data Quality Training

Data quality refers to the features and characteristics of data that determine its usefulness. Key components of data quality include content, form, and dimensions such as accuracy, completeness, reliability, precision, timeliness, integrity, and confidentiality. Common issues with data quality include systematic errors from programming mistakes or poor definitions, and random errors from transcription problems or hardware failure. Ensuring data quality involves initial examination of data for missing values, outliers, and logic as well as routine examination of timeliness and random quality checks verified through facility visits.

Uploaded by

Bancy Ngatia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
279 views9 pages

Data Quality Training

Data quality refers to the features and characteristics of data that determine its usefulness. Key components of data quality include content, form, and dimensions such as accuracy, completeness, reliability, precision, timeliness, integrity, and confidentiality. Common issues with data quality include systematic errors from programming mistakes or poor definitions, and random errors from transcription problems or hardware failure. Ensuring data quality involves initial examination of data for missing values, outliers, and logic as well as routine examination of timeliness and random quality checks verified through facility visits.

Uploaded by

Bancy Ngatia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

Data Quality

What is Data Quality?

All the features and characteristics of a data set that affect its
ability to be useful to its intended purposes, e.g., for analysis.

Components of Data Quality

Content: Accuracy of information

Form: Data stored and presented in a usable way


Dimensions of Data Quality
Accuracy
• Extent to which the data reflect the actual/correct information.

Completeness
• Represents complete list of records (eligible persons, facilities, units) and fields in
each record are provided.

Reliability
• Complete and accurate, consistently measure the intended indicator, and not subject
to inappropriate alteration over time.

Precision
• Sufficient detail provided, e.g., can be disaggregated by gender, age, etc.
Dimensions of Data Quality
Timeliness
• Up-to-date (current) and information is available on time.

Integrity
• System used to generate data is protected from deliberate bias or
manipulation for political or personal reasons.

Confidentiality
• Clients assured their data will be maintained according to national and/or
international standards for data protection.
Issues with Data Quality
Systematic Errors
o Programming mistakes
o Bad definitions for data types or models
o Violations of rules established for data collection
o Poorly defined rules
o Poor training

Random Errors
o Keying errors
o Data transcription problems
o Illegible handwriting
o Hardware failure (e.g., breakdown or corruption)
o Deliberately misleading statements by patients or care providers
Data Quality for SRHR research
Initial examination
o Missing data
o Repeated numbers
o Grouping data over many months (smoothing)
o Outliers
o Internal validity (logic)

Routine examination
o All above data
o Timeliness
o Random data quality checks
Addressing Issues with Data Quality
Missing Data and Outliers

⌖ Visits and phone calls to facilities and counties


to verify reasons for missing and outlying data.

⌖ Use project templates to record verified data


for comparisons with existing data sets.

⌖ Identify and document challenges encountered


in data verification activities for follow-up.
Verification of Reported Data
Stage 1: In-depth Verifications at Facilities
Documentation Review

• Review on availability and completeness of facility documents.

Trace and Verification

• Recounting reported results.

Cross-checking reported results with other


data sources
Verification of Reported Data (contd.)
Stage 2: Follow-up Verifications at sub-Counties and Counties

Documentation Review

• Review on availability and completeness of sub-county and


county documents.

Trace and Verification

• Recounting reported results.


Verification of Reported Data (contd.)
Source Documents and Tools
Primary Registers, tally sheet,
Source patient/client records, and
project templates.
(facility level)

Secondary
Summary forms (MoH tools),
Source electronic databases (DHIS2),
(sub-county and and project templates.
county level)

You might also like